Create app_1.py

app_1.py

@@ -0,0 +1,24 @@
+# pip install -U gradio huggingface_hub
+
+import os
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+MODEL_ID = "Qwen/Qwen3-Coder-Next"
+client = InferenceClient(model=MODEL_ID, token=os.environ.get("HF_TOKEN"))
+
+def chat(user_msg, history):
+    messages = []
+    for u, a in history:
+        messages += [{"role": "user", "content": u}, {"role": "assistant", "content": a}]
+    messages.append({"role": "user", "content": user_msg})
+
+    # Server-side Chat Completions (je nach Backend/Provider)
+    resp = client.chat.completions.create(
+        messages=messages,
+        max_tokens=512,
+        temperature=0.2,
+    )
+    return resp.choices[0].message["content"]
+
+gr.ChatInterface(chat, title="Qwen3-Coder-Next (HF Inference API)").launch()